Some strong limit theorems for the largest entries of sample correlation matrices
Li, Deli ; Rosalsky, Andrew
Ann. Appl. Probab., Tome 16 (2006) no. 1, p. 423-447 / Harvested from Project Euclid
Let {Xk,i;i≥1,k≥1} be an array of i.i.d. random variables and let {pn;n≥1} be a sequence of positive integers such that n/pn is bounded away from 0 and ∞. For Wn=max 1≤in|∑k=1nXk,iXk,j| and Ln=max 1≤in|ρ̂(n)i,j| where ρ̂(n)i,j denotes the Pearson correlation coefficient between (X1,i,…,Xn,i)' and (X1,j,…,Xn,j)', the limit laws (i) $\lim_{n\rightarrow \infty}\frac{W_{n}}{n^{\alpha}}=0$ a.s. (α>1/2), (ii) lim n→∞n1−αLn=0 a.s. (1/2<α≤1), (iii) $\lim_{n\rightarrow \infty}\frac{W_{n}}{\sqrt{n\log n}}=2$ a.s. and (iv) $\lim_{n\rightarrow \infty}(\frac{n}{\log n})^{1/2}L_{n}=2$ a.s. are shown to hold under optimal sets of conditions. These results follow from some general theorems proved for arrays of i.i.d. two-dimensional random vectors. The converses of the limit laws (i) and (iii) are also established. The current work was inspired by Jiang’s study of the asymptotic behavior of the largest entries of sample correlation matrices.
Publié le : 2006-02-14
Classification:  Largest entries of sample correlation matrices,  strong law of large numbers,  law of the logarithm,  almost sure convergence,  60F15,  62H99
@article{1141654293,
     author = {Li, Deli and Rosalsky, Andrew},
     title = {Some strong limit theorems for the largest entries of sample correlation matrices},
     journal = {Ann. Appl. Probab.},
     volume = {16},
     number = {1},
     year = {2006},
     pages = { 423-447},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1141654293}
}
Li, Deli; Rosalsky, Andrew. Some strong limit theorems for the largest entries of sample correlation matrices. Ann. Appl. Probab., Tome 16 (2006) no. 1, pp.  423-447. http://gdmltest.u-ga.fr/item/1141654293/